Top robotics data companies are applied research labs: ego-data post-training beats Apple EgoDex
ATTlKA · x · 2026-10-30
@ckxyz argues the best robotics data companies are effectively applied research labs — if you can't rigorously post-train and evaluate policies on your own data, you're just another data vendor waiting to be commoditized.
The quoted experiment from @MidcenturyAI backs this up: they post-trained Physical Intelligence's π0.5 on their ego-centric data, and it outperformed Apple's EgoDex on LIBERO-10 with equal data volume and matched tasks, environments, and objects. Their results suggest viewpoint diversity and richer action supervision can overcome robot learning's dependence on fixed camera positions.
More from Embodied
- SpAItial launches Echo-3: minutes of phone capture become real-scale 3D Gaussian Splat worlds — rmbrualla · 2026-10-30
- Amazon FAR's DreamFAR: a world model trained from scratch on robot data only, 1,000+ tasks — _krishna_murthy · 2026-10-30
- Tesla FSD demo avoids a stop-sign runner, wins over an Elon-averse mom considering Rivian — BenCostaTesla · 2026-10-30
- XPENG's IRON humanoid robot walks off its new production line — ingliguori · 2026-10-30
- PokeBot's RoboAPI brings zero-shot, natural-language robot control to any compatible arm — haider1 · 2026-10-30
- Tesla Robotaxi hosts Accessibility Day as feedback flows into Cybercab and future products — EricETesla · 2026-10-30